F?D: On understanding the role of deep feature spaces on face generation evaluation

• URL: http://arxiv.org/abs/2305.20048v3
• Date: Fri, 11 Aug 2023 17:26:42 GMT
• Title: F?D: On understanding the role of deep feature spaces on face generation evaluation
• Authors: Krish Kabra, Guha Balakrishnan
• Abstract summary: We study the effect that different deep features and their design choices have on a perceptual metric. A key component of our analysis is the creation of synthetic counterfactual faces using deep face generators.
• Score: 5.655130837404874
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Perceptual metrics, like the Fr\'echet Inception Distance (FID), are widely used to assess the similarity between synthetically generated and ground truth (real) images. The key idea behind these metrics is to compute errors in a deep feature space that captures perceptually and semantically rich image features. Despite their popularity, the effect that different deep features and their design choices have on a perceptual metric has not been well studied. In this work, we perform a causal analysis linking differences in semantic attributes and distortions between face image distributions to Fr\'echet distances (FD) using several popular deep feature spaces. A key component of our analysis is the creation of synthetic counterfactual faces using deep face generators. Our experiments show that the FD is heavily influenced by its feature space's training dataset and objective function. For example, FD using features extracted from ImageNet-trained models heavily emphasize hats over regions like the eyes and mouth. Moreover, FD using features from a face gender classifier emphasize hair length more than distances in an identity (recognition) feature space. Finally, we evaluate several popular face generation models across feature spaces and find that StyleGAN2 consistently ranks higher than other face generators, except with respect to identity (recognition) features. This suggests the need for considering multiple feature spaces when evaluating generative models and using feature spaces that are tuned to nuances of the domain of interest.

Related papers

• Analyzing the Feature Extractor Networks for Face Image Synthesis [0.0]
  This study investigates the behavior of diverse feature extractors -- InceptionV3, CLIP, DINOv2, and ArcFace -- considering a variety of metrics -- FID, KID, Precision&Recall. Experiments include deep-down analysis of the features: $L$ normalization, model attention during extraction, and domain distributions in the feature space.
  arXiv  Detail & Related papers  (2024-06-04T09:41:40Z)
• MDFL: Multi-domain Diffusion-driven Feature Learning [19.298491870280213]
  We present a multi-domain diffusion-driven feature learning network (MDFL) MDFL redefines the effective information domain that the model really focuses on. We demonstrate that MDFL significantly improves the feature extraction performance of high-dimensional data.
  arXiv  Detail & Related papers  (2023-11-16T02:55:21Z)
• Hierarchical Forgery Classifier On Multi-modality Face Forgery Clues [61.37306431455152]
  We propose a novel Hierarchical Forgery for Multi-modality Face Forgery Detection (HFC-MFFD) The HFC-MFFD learns robust patches-based hybrid representation to enhance forgery authentication in multiple-modality scenarios. The specific hierarchical face forgery is proposed to alleviate the class imbalance problem and further boost detection performance.
  arXiv  Detail & Related papers  (2022-12-30T10:54:29Z)
• Dynamic Prototype Mask for Occluded Person Re-Identification [88.7782299372656]
  Existing methods mainly address this issue by employing body clues provided by an extra network to distinguish the visible part. We propose a novel Dynamic Prototype Mask (DPM) based on two self-evident prior knowledge. Under this condition, the occluded representation could be well aligned in a selected subspace spontaneously.
  arXiv  Detail & Related papers  (2022-07-19T03:31:13Z)
• Probabilistic Tracking with Deep Factors [8.030212474745879]
  We show how to use a deep feature encoding in conjunction with generative densities over the features in a factor-graph based, probabilistic tracking framework. We present a likelihood model that combines a learned feature encoder with generative densities over them, both trained in a supervised manner.
  arXiv  Detail & Related papers  (2021-12-02T21:31:51Z)
• Heterogeneous Face Frontalization via Domain Agnostic Learning [74.86585699909459]
  We propose a domain agnostic learning-based generative adversarial network (DAL-GAN) which can synthesize frontal views in the visible domain from thermal faces with pose variations. DAL-GAN consists of a generator with an auxiliary classifier and two discriminators which capture both local and global texture discriminations for better synthesis.
  arXiv  Detail & Related papers  (2021-07-17T20:41:41Z)
• InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs [73.27299786083424]
  We propose a framework called InterFaceGAN to interpret the disentangled face representation learned by state-of-the-art GAN models. We first find that GANs learn various semantics in some linear subspaces of the latent space. We then conduct a detailed study on the correlation between different semantics and manage to better disentangle them via subspace projection.
  arXiv  Detail & Related papers  (2020-05-18T18:01:22Z)
• DotFAN: A Domain-transferred Face Augmentation Network for Pose and Illumination Invariant Face Recognition [94.96686189033869]
  We propose a 3D model-assisted domain-transferred face augmentation network (DotFAN) DotFAN can generate a series of variants of an input face based on the knowledge distilled from existing rich face datasets collected from other domains. Experiments show that DotFAN is beneficial for augmenting small face datasets to improve their within-class diversity.
  arXiv  Detail & Related papers  (2020-02-23T08:16:34Z)
• Dual-Attention GAN for Large-Pose Face Frontalization [59.689836951934694]
  We present a novel Dual-Attention Generative Adversarial Network (DA-GAN) for photo-realistic face frontalization. Specifically, a self-attention-based generator is introduced to integrate local features with their long-range dependencies. A novel face-attention-based discriminator is applied to emphasize local features of face regions.
  arXiv  Detail & Related papers  (2020-02-17T20:00:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.